Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds real semantic context beyond that: it defines what each metric means operationally ('views (public page loads)', 'starts (first field typed)', 'submissions (rows the form added)'), and the schema notes that all-time has no previous period, which prevents a misinterpretation of the comparison fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The metric inventory is front-loaded and every listed item is load-bearing for an agent deciding whether this answers the question. The definition is dense but not padded; the only mild redundancy is enumerating return values that the output schema already encodes.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter read tool with an output schema and full annotations, nothing needed to invoke it correctly is missing: purpose, trigger phrases, and peekId provenance are all present. The overlap between the metric list and the output schema is harmless rather than a completeness gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%: range is fully documented in the schema while peekId has no schema description at all. The description compensates for exactly that gap by explaining what a peekId is and where to obtain it (sheet.schema), which is the higher-value of the two undocumented details. It adds nothing about range, but the schema already handles that parameter completely.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The opening clause names the resource (form) and enumerates the exact metrics returned: views, starts, submissions, previous-period equivalents, median completion time, per-day submissions, and per-question drop-off. An agent can tell this is an analytics-read tool and distinguish it from mutation siblings like form.update or sheet.aggregate without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It supplies two concrete trigger questions ('how is my inquiry form doing?', 'where do people drop off my form?') and a prerequisite step ('Pass the form's peekId (sheet.schema lists a sheet's forms)'), which is genuinely actionable routing guidance. It stops short of naming an alternative or an exclusion (e.g., when to prefer sheet.aggregate or dashboard.read), so it falls just short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.